Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 660 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0855. Min Range: -1.0855

Max Act: 1.0855. Min Act: -0.0001

Data Index: 1088299 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.9981. Min Act: -0.0001

Data Index: 270685 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.8822. Min Act: -0.0001

Data Index: 560659 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.9014. Min Act: -0.0001

Data Index: 810578 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.8177. Min Act: -0.0001

Data Index: 1009675 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.8635. Min Act: -0.0001

Data Index: 63981 (C4 (Web Text))

Max Activating Token Index: 422

Text #6

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.8808. Min Act: -0.0001

Data Index: 1064875 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.8653. Min Act: -0.0001

Data Index: 225449 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.7921. Min Act: -0.0001

Data Index: 668793 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.7825. Min Act: -0.0001

Data Index: 813432 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.7901. Min Act: -0.0001

Data Index: 372702 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.7979. Min Act: -0.0001

Data Index: 1188269 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.9105. Min Act: -0.0001

Data Index: 36073 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.7959. Min Act: -0.0001

Data Index: 634624 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.7866. Min Act: -0.0001

Data Index: 1192715 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.7840. Min Act: -0.0001

Data Index: 114333 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.7615. Min Act: -0.0001

Data Index: 1269341 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.7559. Min Act: -0.0001

Data Index: 497050 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.7331. Min Act: -0.0001

Data Index: 1298491 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.7494. Min Act: -0.0001

Data Index: 977370 (C4 (Web Text))

Max Activating Token Index: 664